隐式神经表示与B样条在从稀疏样本中连续函数拟合中的比较
Comparing Implicit Neural Representations and B-Splines for Continuous Function Fitting from Sparse Samples
AI总结:
本文比较了隐式神经表示与B样条在稀疏样本连续函数拟合中的性能,发现INR在误差和伪影方面表现更优,且双层优化框架能近似最优性能。
摘要:
连续信号表示法在逆问题中(如磁共振成像和计算机断层扫描)具有天然优势,因为测量结果依赖于底层的物理连续信号。尽管传统方法依赖于预定义的分析基函数如B样条,隐式神经表示(INR)作为一种强大的替代方法,使用基于坐标的网络来参数化具有隐式定义基函数的连续函数。尽管在经验上取得了成功,但直接比较其内在表示能力与传统模型的比较仍然有限。本初步经验研究比较了位置编码的INR与立方B样条模型在从稀疏随机样本中进行连续函数拟合时的性能,通过仅使用系数域的Tikhonov正则化来隔离表示能力的差异。结果表明,在最优超参数选择下,INR在归一化均方误差上更低,产生更清晰的边缘过渡和更少的振荡伪影,优于最优调优的B样条模型。此外,我们还展示了基于测量数据分割的实用双层优化框架,可以有效近似最优性能。这些发现经验上支持了INR在稀疏数据拟合中的优越表示能力。
英文摘要:
Continuous signal representations are naturally suited for inverse problems, such as magnetic resonance imaging (MRI) and computed tomography, because the measurements depend on an underlying physically continuous signal. While classical methods rely on predefined analytical bases like B-splines, implicit neural representations (INRs) have emerged as a powerful alternative that use coordinate-based networks to parameterize continuous functions with implicitly defined bases. Despite their empirical success, direct comparisons of their intrinsic representation capabilities with conventional models remain limited. This preliminary empirical study compares a positional-encoded INR with a cubic B-spline model for continuous function fitting from sparse random samples, isolating the representation capacity difference by only using coefficient-domain Tikhonov regularization. Results demonstrate that, under oracle hyperparameter selection, the INR achieves a lower normalized root-mean-squared error, yielding sharper edge transitions and fewer oscillatory artifacts than the oracle-tuned B-spline model. Additionally, we show that a practical bilevel optimization framework for INR hyperparameter selection based on measurement data split effectively approximates oracle performance. These findings empirically support the superior representation capacity of INRs for sparse data fitting.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。